Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses behavior that the annotations do not: that both files are left untouched, that ambiguous duplicate keys are surfaced rather than silently resolved, and that each report costs 0.05 USDC on Base. The pricing/side-effect disclosure is genuinely useful context beyond the readOnlyHint/openWorldHint flags, though it does not explain failure modes for malformed CSVs or oversized inputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler: the core operation and its outputs come first, with the non-mutation guarantee and price appended. Every clause carries information an agent needs before calling the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates the report contents (changed values, missing rows, duplicate keys), which substitutes for a return-value spec. Combined with the cost and non-destructive guarantee, an agent has enough to call it correctly; only error/edge-case behavior is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75%, so the schema already documents left_csv/right_csv size limits and compare_columns defaults and the empty-list semantics. The description only alludes to 'shared key columns', adding no format, delimiter, or encoding detail beyond what the schema states. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Compare two CSV tables by shared key columns') and enumerates the exact findings produced: changed values, missing rows, ambiguous duplicate keys. The sibling tools (demo, ping, service_info) are unrelated utilities, so no further differentiation is needed for an agent to pick this one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for when this tool applies — reconciling two CSV tables by shared keys — and adds the constraint that neither file is edited, which tells an agent this is safe to invoke on live data. It stops short of explicit when-not guidance or naming an alternative approach, but no sibling overlaps this function.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.